Applied AI/ML Scientist - BeamUP

4+ years of experience in applied data science or ML in a product environment, with demonstrated experience building agentic systems or autonomous agents MSc in Computer Science, Data Science, Mathematics, Statistics, Engineering, or a related field (or equivalent practical experience) Proven track record designing and implementing multi-step agentic pipelines, including LLM-based agents, tool use, planning loops, and memory mechanisms Hands-on experience with agentic frameworks such as LangChain, LangGraph, AutoGen, or equivalent Strong Python coding skills; familiar with Spark for large-scale, distributed data processing Experience with LLM APIs (e.g., OpenAI, Anthropic, Bedrock, open-source models) and prompt engineering for agentic use cases Experience performing rigorous model evaluation (baselines, cross-validation, error analysis) and defining evaluation strategies for agent behavior Strong communication and collaboration skills; able to work across engineering, product, and supply chain domain experts and iterate fast

Design and build autonomous agentic systems that generate, configure, and execute analytical pipelines to solve supply chain challenges end-to-end Architect multi-agent workflows with planning, tool use, memory, and feedback loops, enabling agents to reason, adapt, and improve over time Develop and integrate ML and deep learning models (e.g., predictive models, anomaly detection, demand forecasting) as core capabilities within agentic pipelines Research and apply state-of-the-art techniques in agentic AI, LLM orchestration, and multi-agent systems to production use cases Translate complex logistics and supply chain challenges into agent-based problem formulations, collaborating closely with product and domain experts Define and implement rigorous evaluation frameworks for agent performance: correctness, reliability, robustness, and edge-case handling Collaborate with software engineers to productize agentic solutions - including testing, monitoring, versioning, and iterative improvement Contribute to team practices: reproducible code, experiment tracking, documentation, and knowledge sharing

4+ years of experience in applied data science or ML in a product environment, with demonstrated experience building agentic systems or autonomous agents MSc in Computer Science, Data Science, Mathematics, Statistics, Engineering, or a related field (or equivalent practical experience) Proven track record designing and implementing multi-step agentic pipelines, including LLM-based agents, tool use, planning loops, and memory mechanisms Hands-on experience with agentic frameworks such as LangChain, LangGraph, AutoGen, or equivalent Strong Python coding skills; familiar with Spark for large-scale, distributed data processing Experience with LLM APIs (e.g., OpenAI, Anthropic, Bedrock, open-source models) and prompt engineering for agentic use cases Experience performing rigorous model evaluation (baselines, cross-validation, error analysis) and defining evaluation strategies for agent behavior Strong communication and collaboration skills; able to work across engineering, product, and supply chain domain experts and iterate fast